set_pbir_visual_format

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and does well. It discloses the merging behavior ('merged into its objects tree'), explains the two value modes (scalar vs. JSON verbatim), and gives concrete examples (measure-bound expr, FillRule, image, gradient stops). It does not mention error handling or permissions, but the core behavior is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is information-dense yet concise, with no filler. It front-loads the core purpose, then defines the key terms (card, bucket, value) in a logical flow. Every sentence adds value, and the examples are efficiently packed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 8 parameters and no output schema, the description covers the tricky parts: the merging behavior, valueIsJson handling, and the distinction between bucket types. It does not describe return values or error scenarios, but those are not implicit requirements for a property-setting tool. Slight gap: it could mention what the tool doesn't do (e.g., not for bulk updates) explicitly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 88%, and the description significantly enriches the parameters. It clarifies 'card' as a formatting object with examples, 'bucket' as objects vs. visualContainerObjects, and 'value' with scalar/JSON modes and concrete JSON node examples. This goes well beyond the schema's brief descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's specific action: 'Set ONE formatting property on a PBIR visual, merged into its objects tree via the shared encoder.' It distinguishes itself from generic formatting tools by emphasizing the singular property scope and the merging mechanism. The examples 'legend, dataLabels, title, background' ground the abstract card concept.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use the tool: for setting exactly one formatting property at a time, with detailed guidance on card and bucket semantics. It does not explicitly name alternative tools for multi-property changes, but the 'ONE' emphasis and the card/bucket explanation effectively communicate its intended scope.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.